{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T14:10:32Z","timestamp":1759759832121,"version":"build-2065373602"},"publisher-location":"Berlin, Heidelberg","reference-count":40,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783662722428","type":"print"},{"value":"9783662722435","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,4]],"date-time":"2025-10-04T00:00:00Z","timestamp":1759536000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,4]],"date-time":"2025-10-04T00:00:00Z","timestamp":1759536000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-662-72243-5_6","type":"book-chapter","created":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T13:28:40Z","timestamp":1759757320000},"page":"95-111","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Gradient Similarity Surgery in\u00a0Multi-task Deep Learning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-9541-890X","authenticated-orcid":false,"given":"Thomas","family":"Borsani","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2622-6776","authenticated-orcid":false,"given":"Andrea","family":"Rosani","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0650-3157","authenticated-orcid":false,"given":"Giuseppe","family":"Nicosia","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3096-2844","authenticated-orcid":false,"given":"Giuseppe","family":"Di Fatta","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,10,4]]},"reference":[{"key":"6_CR1","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1023\/A:1007379606734","volume":"28","author":"R Caruana","year":"1997","unstructured":"Caruana, R.: Multitask learning. Mach. Learn. 28, 41\u201375 (1997)","journal-title":"Mach. Learn."},{"key":"6_CR2","unstructured":"Chen, Z., Badrinarayanan, V., Lee, C.Y., Rabinovich, A.: GradNorm: gradient normalization for adaptive loss balancing in deep multitask networks. In: Proceedings of the 35th International Conference on Machine Learning, vol.\u00a080, pp. 794\u2013803 (2018)"},{"key":"6_CR3","unstructured":"Chen, Z., et al.: Just pick a sign: optimizing deep multitask models with gradient sign dropout. In: Advances in Neural Information Processing Systems, vol.\u00a033, pp. 2039\u20132050 (2020)"},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Choi, W., Shin, M., Lee, H., Cho, J., Park, J., Im, S.: Multi-task learning for real-time autonomous driving leveraging task-adaptive attention generator. In: IEEE International Conference on Robotics and Automation (ICRA), pp. 14732\u201314739 (2024)","DOI":"10.1109\/ICRA57147.2024.10610716"},{"key":"6_CR5","doi-asserted-by":"crossref","unstructured":"Cipolla, R., Gal, Y., Kendall, A.: Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7482\u20137491 (2018)","DOI":"10.1109\/CVPR.2018.00781"},{"key":"6_CR6","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"6_CR7","unstructured":"Di\u00a0Fatta, G., Nicosia, G., Ojha, V., Pardalos, P.: Multi-task deep learning as multi-objective optimization. In: Encyclopedia of Optimization (2020)"},{"key":"6_CR8","doi-asserted-by":"crossref","unstructured":"Dong, D., Wu, H., He, W., Yu, D., Wang, H.: Multi-task learning for multiple language translation. In: Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp. 1723\u20131732 (2015)","DOI":"10.3115\/v1\/P15-1166"},{"key":"6_CR9","doi-asserted-by":"crossref","unstructured":"Dong, X., et al.: GDOD: effective gradient descent using orthogonal decomposition for multi-task learning. In: Proceedings of the 31st ACM International Conference on Information & Knowledge Management, pp. 386\u2013395 (2022)","DOI":"10.1145\/3511808.3557333"},{"issue":"5","key":"6_CR10","doi-asserted-by":"publisher","first-page":"313","DOI":"10.1016\/j.crma.2012.03.014","volume":"350","author":"JA D\u00e9sid\u00e9ri","year":"2012","unstructured":"D\u00e9sid\u00e9ri, J.A.: Multiple-gradient descent algorithm (MGDA) for multiobjective optimization. C. R. Math. 350(5), 313\u2013318 (2012)","journal-title":"C. R. Math."},{"key":"6_CR11","doi-asserted-by":"crossref","unstructured":"Elich, C., Kirchdorfer, L., K\u00f6hler, J.M., Schott, L.: Examining common paradigms in multi-task learning. In: Pattern Recognition, pp. 131\u2013147 (2025)","DOI":"10.1007\/978-3-031-85181-0_9"},{"key":"6_CR12","unstructured":"Fifty, C., Amid, E., Zhao, Z., Yu, T., Anil, R., Finn, C.: Efficiently identifying task groupings for multi-task learning. In: Advances in Neural Information Processing Systems, vol.\u00a034, pp. 27503\u201327516 (2021)"},{"key":"6_CR13","doi-asserted-by":"crossref","unstructured":"Guo, M., Haque, A., Huang, D.A., Yeung, S., Fei-Fei, L.: Dynamic task prioritization for multitask learning. In: Proceedings of the European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-01270-0_17"},{"issue":"12","key":"6_CR14","doi-asserted-by":"publisher","first-page":"3969","DOI":"10.1109\/TMI.2022.3202183","volume":"41","author":"J Hao","year":"2022","unstructured":"Hao, J., et al.: Retinal structure detection in octa image via voting-based multitask learning. IEEE Trans. Med. Imaging 41(12), 3969\u20133980 (2022)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"6_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1007\/978-3-031-47401-9_12","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2023 Workshops","author":"S Kim","year":"2023","unstructured":"Kim, S., Purdie, T.G., McIntosh, C.: Cross-task attention network: improving multi-task learning for medical imaging applications. In: Celebi, M.E., et al. (eds.) MICCAI 2023. LNCS, vol. 14393, pp. 119\u2013128. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-47401-9_12"},{"key":"6_CR16","unstructured":"Kingma, D.P.: Adam: a method for stochastic optimization. The third International Conference on Learning Representations (2015)"},{"key":"6_CR17","doi-asserted-by":"crossref","unstructured":"Kuhn, H.W., Tucker, A.W.: Nonlinear programming. In: Proceedings of the Second Berkeley Symposium on Mathematical Statistics and Probability (1951)","DOI":"10.1525\/9780520411586-036"},{"key":"6_CR18","unstructured":"Lin, B., Ye, F., Zhang, Y., Tsang, I.W.: Reasonable effectiveness of random weighting: a litmus test for multi-task learning. Trans. Mach. Learn. Res. 2835\u20138856 (2022)"},{"key":"6_CR19","unstructured":"Liu, B., Feng, Y., Stone, P., Liu, Q.: FAMO: fast adaptive multitask optimization. In: Advances in Neural Information Processing Systems, vol.\u00a036, pp. 57226\u201357243 (2023)"},{"key":"6_CR20","unstructured":"Liu, B., Liu, X., Jin, X., Stone, P., Liu, Q.: Conflict-averse gradient descent for multi-task learning. In: Advances in Neural Information Processing Systems, vol.\u00a034, pp. 18878\u201318890 (2021)"},{"key":"6_CR21","unstructured":"Liu, L., et al.: Towards impartial multi-task learning. In: International Conference on Learning Representations (2021)"},{"key":"6_CR22","doi-asserted-by":"crossref","unstructured":"Liu, S., Johns, E., Davison, A.J.: End-to-end multi-task learning with attention. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1871\u20131880 (2019)","DOI":"10.1109\/CVPR.2019.00197"},{"key":"6_CR23","doi-asserted-by":"crossref","unstructured":"Liu, Z., Luo, P., Wang, X., Tang, X.: Deep learning face attributes in the wild. In: Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV), pp. 3730\u20133738 (2015)","DOI":"10.1109\/ICCV.2015.425"},{"key":"6_CR24","unstructured":"Navon, A., et al.: Multi-task learning as a bargaining game. In: Proceedings of the 39th International Conference on Machine Learning, vol.\u00a0162, pp. 16428\u201316446 (2022)"},{"key":"6_CR25","doi-asserted-by":"publisher","first-page":"120587","DOI":"10.1016\/j.eswa.2023.120587","volume":"230","author":"J Ong","year":"2023","unstructured":"Ong, J., Herremans, D.: Constructing time-series momentum portfolios with deep multi-task learning. Expert Syst. Appl. 230, 120587 (2023)","journal-title":"Expert Syst. Appl."},{"key":"6_CR26","unstructured":"Ruder, S.: An overview of multi-task learning in deep neural networks (2017). http:\/\/arxiv.org\/abs\/1706.05098"},{"key":"6_CR27","doi-asserted-by":"crossref","unstructured":"Senushkin, D., Patakin, N., Kuznetsov, A., Konushin, A.: Independent component alignment for multi-task learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 20083\u201320093 (2023)","DOI":"10.1109\/CVPR52729.2023.01923"},{"key":"6_CR28","unstructured":"Shen, J., Zhen, X., Worring, M., Shao, L.: Variational multi-task learning with gumbel-softmax priors. In: Advances in Neural Information Processing Systems, vol.\u00a034, pp. 21031\u201321042 (2021)"},{"key":"6_CR29","unstructured":"SHI, G., Li, Q., Zhang, W., Chen, J., Wu, X.M.: Recon: reducing conflicting gradients from the root for multi-task learning. In: The Eleventh International Conference on Learning Representations (2023)"},{"key":"6_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"746","DOI":"10.1007\/978-3-642-33715-4_54","volume-title":"Computer Vision \u2013 ECCV 2012","author":"N Silberman","year":"2012","unstructured":"Silberman, N., Hoiem, D., Kohli, P., Fergus, R.: Indoor segmentation and support inference from RGBD images. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7576, pp. 746\u2013760. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33715-4_54"},{"key":"6_CR31","unstructured":"Sodhani, S., Zhang, A., Pineau, J.: Multi-task reinforcement learning with context-based representations. In: Proceedings of the 38th International Conference on Machine Learning, vol.\u00a0139, pp. 9767\u20139779 (2021)"},{"key":"6_CR32","unstructured":"Standley, T., Zamir, A., Chen, D., Guibas, L., Malik, J., Savarese, S.: Which tasks should be learned together in multi-task learning? In: Proceedings of the 37th International Conference on Machine Learning, vol.\u00a0119, pp. 9120\u20139132 (2020)"},{"issue":"7","key":"6_CR33","doi-asserted-by":"publisher","first-page":"9579","DOI":"10.1109\/TNNLS.2023.3234166","volume":"35","author":"Y Tian","year":"2024","unstructured":"Tian, Y., Bai, K.: End-to-end multitask learning with vision transformer. IEEE Trans. Neural Netw. Learn. Syst. 35(7), 9579\u20139590 (2024)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"6_CR34","doi-asserted-by":"crossref","unstructured":"Wang, A., Singh, A., Michael, J., Hill, F., Levy, O., Bowman, S.: GLUE: a multi-task benchmark and analysis platform for natural language understanding. In: Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pp. 353\u2013355 (2018)","DOI":"10.18653\/v1\/W18-5446"},{"key":"6_CR35","doi-asserted-by":"crossref","unstructured":"Wulfmeier, M., et al.: Compositional transfer in hierarchical reinforcement learning. In: Proceedings of Robotics: Science and Systems (2020)","DOI":"10.15607\/RSS.2020.XVI.054"},{"key":"6_CR36","unstructured":"Yang, R., Xu, H., WU, Y., Wang, X.: Multi-task reinforcement learning with soft modularization. In: Advances in Neural Information Processing Systems, vol.\u00a033, pp. 4767\u20134777 (2020)"},{"key":"6_CR37","unstructured":"Yu, T., Kumar, S., Gupta, A., Levine, S., Hausman, K., Finn, C.: Gradient surgery for multi-task learning. In: Advances in Neural Information Processing Systems, vol.\u00a033, pp. 5824\u20135836 (2020)"},{"key":"6_CR38","unstructured":"Yu, T., Quillen, D., He, Z., Julian, R., Hausman, K., Finn, C., Levine, S.: Meta-world: a benchmark and evaluation for multi-task and meta reinforcement learning. In: Proceedings of the Conference on Robot Learning (2020)"},{"key":"6_CR39","doi-asserted-by":"crossref","unstructured":"Zamir, A.R., Sax, A., Shen, W., Guibas, L.J., Malik, J., Savarese, S.: Taskonomy: disentangling task transfer learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00391"},{"key":"6_CR40","unstructured":"Zhuang, J., et al.: AdaBelief optimizer: adapting stepsizes by the belief in observed gradients. In: Advances in Neural Information Processing Systems, vol.\u00a033, pp. 18795\u201318806 (2020)"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases. Research Track and Applied Data Science Track"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-662-72243-5_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T13:28:49Z","timestamp":1759757329000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-662-72243-5_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,4]]},"ISBN":["9783662722428","9783662722435"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-662-72243-5_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,4]]},"assertion":[{"value":"4 October 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Porto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portugal","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ecmlpkdd.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}